Confabulation based sentence completion for machine reading

Abstract

Sentence completion and prediction refers to the capability of filling missing words in any incomplete sentences. It is one of the keys to reading comprehension, thus making sentence completion an indispensible component of machine reading. Cogent confabulation is a bio-inspired computational model that mimics the human information processing. The building of confabulation knowledge base uses an unsupervised machine learning algorithm that extracts the relations between objects at the symbolic level. In this work, we propose performance improved training and recall algorithms that apply the cogent confabulation model to solve the sentence completion problem. Our training algorithm adopts a two-level hash table, which significantly improves the training speed, so that a large knowledge base can be built at relatively low computation cost. The proposed recall function fills missing words based on the sentence context. Experimental results show that our software can complete trained sentences with 100% accuracy. It also gives semantically correct answers to more than two thirds of the testing sentences that have not been trained before.

Unified perception-prediction model for context aware text recognition on a heterogeneous many-core platform

“…Two level hash functions are used to speed up the training and recall of the sentence level confabulation model. More details of sentence level confabulation can be found in our recent work [6].…”

“…In the other category, models and algorithms are researched to operate on the concept-level objects, assuming that they have already been "recognized" or extracted from raw inputs. In a recent development, the cogent confabulation model was used for sentence completion [5] [6]. Trained using a large amount of literatures, the confabulation algorithm has demonstrated the capability of completing a sentence (given a few starting words) based on conditional probabilities among the words and phrases.…”

Integration, Development and Performance of the 500 TFLOPS Heterogeneous Cluster (Condor)

“…NEUROMORPHIC COMPUTING: Brain-inspired signal processing algorithms and flow possess great potentials to be applied to many cognitive applications such as image processing, intrusion detection, etc. To investigate the software and hardware requirements of this new information processing approach, a proof-of-concept prototype of context-aware Intelligence Text Recognition Software (ITRS) was developed on the Condor HPC [1]. The software architecture of ITRS incorporates the Condor HPC technologies with advances in neuromorphic computing models.…”

An Exploratory Approach to Find a Novel Metric Based Optimum Language Model for Automatic Bangla Word Prediction

“…At [15] software with improved training and recall algorithms are suggested to solve the sentence completion problem using the cogent confabulation model, which can remember sentences with 100% accuracy in the training files. In addition, it helps in filling up missing words in simple sentences or based on some given initial words deliver meaningful sentences.…”